Bio-inspired computer vision model for event detection

The goal of this project was to build a computer vision model with visual event detection capabilities, close to the human ones. This model had to meet four key requirements: (i) be able to determine an scene saliency map, (ii) obtain from this map, the scan sequence in order of visual importance, (iii) possess the ability to modulate the attention in accordance with the specified task, and (iv) allowing real-time monitoring of objects which get the attention.